Abstract
This dataset is for the validation of a second language (L2) student engagement scale in the English as a foreign language (EFL) context of Vietnam. Based on a cross-sectional design, data were collected from 276 undergraduate English majors at a university in the Mekong Delta of Vietnam using convenience sampling. A 21-item self-report questionnaire served as the sole instrument for data collection. It included four theoretically grounded engagement dimensions: behavioral, cognitive, emotional, and agentic. The instrument underwent a rigorous process of content validation, pilot testing, and psychometric evaluation. Preliminary screening confirmed that the data were complete, normally distributed, and free of univariate and multivariate outliers. Reliability tests yielded excellent internal consistency of the overall scale and its subcomponents. The four-factor structure was confirmed through Exploratory Factor Analysis, which explained 77.1% of the total variance. It was subsequently validated using Confirmatory Factor Analysis, with results showing excellent model fit. The dataset provides a validated measurement tool for assessing engagement among L2 students and may facilitate cross-cultural comparisons, meta-analytic syntheses, and future replication studies of student engagement in applied linguistics and L2 education.
